Learn R Programming

keras (version 2.16.1)

R Interface to 'Keras'

Description

Interface to 'Keras' , a high-level neural networks 'API'. 'Keras' was developed with a focus on enabling fast experimentation, supports both convolution based networks and recurrent networks (as well as combinations of the two), and runs seamlessly on both 'CPU' and 'GPU' devices.

Copy Link

Version

Install

install.packages('keras')

Monthly Downloads

17,691

Version

2.16.1

License

MIT + file LICENSE

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/rstudio/keras3/tree/r2

Homepage

https://tensorflow.rstudio.com/

Maintainer

Tomasz Kalinowski

Last Published

February 14th, 2026

Functions in keras (2.16.1)

(Deprecated) Create a custom Layer

Fits the state of the preprocessing layer to the data being passed

application_efficientnet

Instantiates the EfficientNetB0 architecture

activation_relu

Activation functions

application_densenet

Instantiates the DenseNet architecture.

(Deprecated) Base R6 class for Keras wrappers

KerasConstraint

(Deprecated) Base R6 class for Keras constraints

(Deprecated) Base R6 class for Keras layers

(Deprecated) Base R6 class for Keras callbacks

Keras backend tensor engine

application_resnet

Instantiates the ResNet architecture

application_xception

Instantiates the Xception architecture

application_inception_v3

Inception V3 model, with weights pre-trained on ImageNet.

application_mobilenet_v2

MobileNetV2 model architecture

application_nasnet

Instantiates a NASNet model.

application_inception_resnet_v2

Inception-ResNet v2 model, with weights trained on ImageNet

application_vgg

VGG16 and VGG19 models for Keras.

application_mobilenet

MobileNet model architecture.

application_mobilenet_v3

Instantiates the MobileNetV3Large architecture

callback_model_checkpoint

Save the model after every epoch.

callback_lambda

Create a custom callback

Bidirectional wrapper for RNNs

callback_csv_logger

Callback that streams epoch results to a csv file

callback_reduce_lr_on_plateau

Reduce learning rate when a metric has stopped improving.

callback_remote_monitor

Callback used to stream events to a server.

callback_learning_rate_scheduler

Learning rate scheduler.

Create a Keras Layer

(Deprecated) Create a Keras Wrapper

Custom metric function

callback_backup_and_restore

Callback to back up and restore the training state

create_layer_wrapper

Create a Keras Layer wrapper

callback_progbar_logger

Callback that prints metrics to stdout.

dataset_cifar100

CIFAR100 small image classification

dataset_fashion_mnist

Fashion-MNIST database of fashion articles

IMDB Movie reviews sentiment classification

Weight constraints

Count the total number of scalars composing the weights.

callback_early_stopping

Stop training when a monitored quantity has stopped improving.

MNIST database of handwritten digits

Clone a model instance.

compile.keras.engine.training.Model

Configure a Keras model for training

dataset_boston_housing

Boston housing price regression dataset

dataset_reuters

Reuters newswire topics classification

evaluate.keras.engine.training.Model

Evaluate a Keras model

dataset_cifar10

CIFAR10 small image classification

Freeze and unfreeze weights

flow_images_from_directory

Generates batches of data from images in a directory (with optional augmented/normalized data)

Retrieve the next item from a generator

Retrieve tensors for layers with multiple nodes

Downloads a file from a URL if it not already in the cache.

fit.keras.engine.training.Model

Train a Keras model

Layer/Model weights as R arrays

(Deprecated) Fits the model on data yielded batch-by-batch by a generator.

Retrieves a layer based on either its name (unique) or index.

fit_image_data_generator

Fit image data generator internal statistics to some sample data.

callback_tensorboard

TensorBoard basic visualizations

export_savedmodel.keras.engine.training.Model

Export a Saved Model

fit_text_tokenizer

Update tokenizer internal vocabulary based on a list of texts or list of sequences.

evaluate_generator

(Deprecated) Evaluates the model on a data generator.

callback_terminate_on_naan

Callback that terminates training when a NaN loss is encountered.

Layer/Model configuration

3D array representation of images

image_data_generator

Deprecated Generate batches of image data with real-time data augmentation. The data will be looped over (in batches).

Representation of HDF5 dataset to be used instead of an R array

flow_images_from_data

Generates batches of augmented/normalized data from image data and labels

flow_images_from_dataframe

Takes the dataframe and the path to a directory and generates batches of augmented/normalized data.

image_dataset_from_directory

Create a dataset from a directory

Loads an image into PIL format.

initializer_identity

Initializer that generates the identity matrix.

initializer_he_uniform

He uniform variance scaling initializer.

imagenet_preprocess_input

Preprocesses a tensor or array encoding a batch of images.

initializer_glorot_uniform

Glorot uniform initializer, also called Xavier uniform initializer.

initializer_he_normal

He normal initializer.

initializer_truncated_normal

Initializer that generates a truncated normal distribution.

initializer_variance_scaling

Initializer capable of adapting its scale to the shape of weights.

initializer_lecun_normal

LeCun normal initializer.

initializer_lecun_uniform

LeCun uniform initializer.

Make an Active Binding

initializer_glorot_normal

Glorot normal initializer, also called Xavier normal initializer.

Make a python class constructor

initializer_constant

Initializer that generates tensors initialized to a constant value.

Bitwise reduction (logical AND).

initializer_random_uniform

Initializer that generates tensors with a uniform distribution.

Bitwise reduction (logical OR).

initializer_random_normal

Initializer that generates tensors with a normal distribution.

Keras implementation

Active Keras backend

Returns the index of the minimum value along an axis.

initializer_zeros

Initializer that generates tensors initialized to 0.

k_batch_get_value

Returns the value of more than one tensor variable.

imagenet_decode_predictions

Decodes the prediction of an ImageNet model.

Returns the static number of elements in a Keras variable or tensor.

is_keras_available

Check if Keras is Available

Install TensorFlow and Legacy Keras, including all Python dependencies

Element-wise absolute value.

k_ctc_batch_cost

Runs CTC loss algorithm on each batch element.

k_batch_normalization

Applies batch normalization on x given mean, var, beta and gamma.

k_cast_to_floatx

Cast an array to the default Keras float type.

Creates a 1D tensor containing a sequence of integers.

initializer_ones

Initializer that generates tensors initialized to 1.

Returns the index of the maximum value along an axis.

initializer_orthogonal

Initializer that generates a random orthogonal matrix.

k_categorical_crossentropy

Categorical crossentropy between an output tensor and a target tensor.

Cumulative product of the values in a tensor, alongside the specified axis.

Instantiate an identity matrix and returns it.

1D convolution.

Batchwise dot product.

Element-wise equality between two tensors.

Cumulative sum of the values in a tensor, alongside the specified axis.

Evaluates the value of a variable.

k_batch_flatten

Turn a nD tensor into a 2D tensor with same 1st dimension.

k_clear_session

Destroys the current TF graph and creates a new one.

k_batch_set_value

Sets the values of many tensor variables at once.

Element-wise value clipping.

k_conv3d_transpose

3D deconvolution (i.e. transposed convolution).

Adds a bias vector to a tensor.

Decodes the output of a softmax.

Casts a tensor to a different dtype and returns it.

2D convolution.

Concatenates a list of tensors alongside the specified axis.

Creates a constant tensor.

k_binary_crossentropy

Binary crossentropy between an output tensor and a target tensor.

k_ctc_label_dense_to_sparse

Converts CTC labels from dense to sparse.

Multiplies 2 tensors (and/or variables) and returns a tensor.

k_depthwise_conv2d

Depthwise 2D convolution with separable filters.

Reduce elems using fn to combine them from right to left.

Segment-wise linear approximation of sigmoid.

Flatten a tensor.

Retrieves the elements of indices indices in the tensor reference.

Get the uid for the default graph.

Instantiates a Keras function

k_image_data_format

Default image data format convention ('channels_first' or 'channels_last').

Element-wise truth value of (x < y).

k_learning_phase

Returns the learning phase flag.

TF session to be used by the backend.

k_in_test_phase

Selects x in test phase, and alt otherwise.

3D convolution.

Element-wise exponential.

Fuzz factor used in numeric expressions.

k_conv2d_transpose

2D deconvolution (i.e. transposed convolution).

Adds a 1-sized dimension at index axis.

Exponential linear unit.

k_moving_average_update

Compute the moving average of a variable.

Returns the number of axes in a tensor, as an integer.

k_random_binomial

Returns a tensor with random binomial distribution of values.

k_random_normal

Returns a tensor with normal distribution of values.

k_is_placeholder

Returns whether x is a placeholder.

Default float type

Returns whether a tensor is a sparse tensor.

Element-wise inequality between two tensors.

k_normalize_batch_in_training

Computes mean and std for batch then apply batch_normalization on batch.

Reverse a tensor along the specified axes.

Repeats a 2D tensor.

k_repeat_elements

Repeats the elements of a tensor along an axis.

Element-wise truth value of (x <= y).

Apply 1D conv with un-shared weights.

Returns the value of a variable.

Returns a tensor with the same content as the input tensor.

k_get_variable_shape

Returns the shape of a variable.

Returns the dtype of a Keras tensor or variable, as a string.

Computes cos of x element-wise.

Sets entries in x to zero at random, while scaling the entire tensor.

Returns the shape of tensor or variable as a list of int or NULL entries.

k_is_keras_tensor

Returns whether x is a Keras tensor.

Reduce elems using fn to combine them from left to right.

Element-wise truth value of (x > y).

k_greater_equal

Element-wise truth value of (x >= y).

Iterates over the time dimension of a tensor

Sum of the values in a tensor, alongside the specified axis.

Computes the one-hot representation of an integer tensor.

Instantiates an all-ones variable of the same shape as another tensor.

Instantiates an all-ones tensor variable and returns it.

k_permute_dimensions

Permutes axes in a tensor.

Switches between two operations depending on a scalar value.

Variance of a tensor, alongside the specified axis.

Element-wise exponentiation.

Maximum value in a tensor.

Reset graph identifiers.

Map the function fn over the elements elems and return the outputs.

k_in_train_phase

Selects x in train phase, and alt otherwise.

Returns whether the targets are in the top k predictions.

Apply 2D conv with un-shared weights.

Element-wise log.

Minimum value in a tensor.

Instantiates a variable and returns it.

Element-wise minimum of two tensors.

Normalizes a tensor wrt the L2 norm alongside the specified axis.

(Deprecated) Computes log(sum(exp(elements across dimensions of a tensor))).

k_manual_variable_initialization

Sets the manual variable initialization flag.

Returns the gradients of variables w.r.t. loss.

Returns whether x is a symbolic tensor.

k_random_uniform

Returns a tensor with uniform distribution of values.

k_separable_conv2d

2D convolution with separable filters.

Element-wise rounding to the closest integer.

k_random_normal_variable

Instantiates a variable with values drawn from a normal distribution.

Softsign of a tensor.

Standard deviation of a tensor, alongside the specified axis.

Softmax of a tensor.

layer_activation

Apply an activation function to an output.

k_sparse_categorical_crossentropy

Categorical crossentropy with integer targets.

R interface to Keras

Softplus of a tensor.

Mean of a tensor, alongside the specified axis.

Element-wise maximum of two tensors.

Instantiates a placeholder tensor and returns it.

k_resize_images

Resizes the images contained in a 4D tensor.

Multiplies the values in a tensor, alongside the specified axis.

Prints message and the tensor value when evaluated.

Main Keras module

Element-wise sign.

k_set_learning_phase

Sets the learning phase to a fixed value.

Rectified linear unit.

k_resize_volumes

Resizes the volume contained in a 5D tensor.

k_random_uniform_variable

Instantiates a variable with values drawn from a uniform distribution.

Reshapes a tensor to the specified shape.

Computes sin of x element-wise.

Stacks a list of rank R tensors into a rank R+1 tensor.

Removes a 1-dimension from the tensor at index axis.

layer_additive_attention

Additive attention layer, a.k.a. Bahdanau-style attention

Sets the value of a variable, from an R array.

layer_activation_elu

Exponential Linear Unit.

Element-wise square root.

layer_alpha_dropout

Applies Alpha Dropout to the input.

layer_category_encoding

A preprocessing layer which encodes integer features.

Creates a tensor by tiling x by n.

Element-wise square.

layer_center_crop

Crop the central portion of the images to target height and width

Transposes a tensor and returns it.

k_truncated_normal

Returns a tensor with truncated random normal distribution of values.

layer_activation_relu

Rectified Linear Unit activation function

layer_average_pooling_3d

Average pooling operation for 3D data (spatial or spatio-temporal).

layer_batch_normalization

Layer that normalizes its inputs

layer_conv_lstm_2d

Convolutional LSTM.

Converts a sparse tensor into a dense tensor and returns it.

Unstack rank R tensor into a list of rank R-1 tensors.

Applies Dropout to the input.

Layer that computes a dot product between samples in two tensors.

layer_conv_lstm_3d

3D Convolutional LSTM

layer_average_pooling_1d

Average pooling for temporal data.

layer_activation_selu

Scaled Exponential Linear Unit.

layer_activation_parametric_relu

Parametric Rectified Linear Unit.

Instantiates an all-zeros variable and returns it.

Instantiates an all-zeros variable of the same shape as another tensor.

k_stop_gradient

Returns variables but with zero gradient w.r.t. every other variable.

layer_activation_leaky_relu

Leaky version of a Rectified Linear Unit.

layer_average_pooling_2d

Average pooling operation for spatial data.

2D convolution layer (e.g. spatial convolution over images).

layer_conv_1d_transpose

Transposed 1D convolution layer (sometimes called Deconvolution).

Layer that averages a list of inputs.

layer_attention

Dot-product attention layer, a.k.a. Luong-style attention

layer_concatenate

Layer that concatenates a list of inputs.

layer_cropping_2d

Cropping layer for 2D input (e.g. picture).

layer_cropping_1d

Cropping layer for 1D input (e.g. temporal sequence).

1D convolution layer (e.g. temporal convolution).

layer_cropping_3d

Cropping layer for 3D data (e.g. spatial or spatio-temporal).

layer_dense_features

Constructs a DenseFeatures.

layer_cudnn_gru

(Deprecated) Fast GRU implementation backed by CuDNN.

layer_depthwise_conv_1d

Depthwise 1D convolution

A preprocessing layer which hashes and bins categorical features.

layer_layer_normalization

Layer normalization layer (Ba et al., 2016).

layer_activation_softmax

Softmax activation function.

keras_model_sequential

Keras Model composed of a linear stack of layers

keras_model_custom

(Deprecated) Create a Keras custom model

Update the value of x to new_x.

layer_activation_thresholded_relu

Thresholded Rectified Linear Unit.

layer_lstm_cell

Cell class for the LSTM layer

layer_locally_connected_1d

Locally-connected layer for 1D inputs.

Masks a sequence by using a mask value to skip timesteps.

layer_global_average_pooling_3d

Global Average pooling operation for 3D data.

layer_global_max_pooling_1d

Global max pooling operation for temporal data.

layer_integer_lookup

A preprocessing layer which maps integer features to contiguous ranges.

Wraps arbitrary expression as a layer

layer_conv_2d_transpose

Transposed 2D convolution layer (sometimes called Deconvolution).

3D convolution layer (e.g. spatial convolution over volumes).

layer_cudnn_lstm

(Deprecated) Fast LSTM implementation backed by CuDNN.

Layer that computes the minimum (element-wise) a list of inputs.

layer_multi_head_attention

MultiHeadAttention layer

layer_random_contrast

Adjust the contrast of an image or images by a random factor

layer_random_crop

Randomly crop the images to target height and width

layer_conv_lstm_1d

1D Convolutional LSTM

layer_embedding

Turns positive integers (indexes) into dense vectors of fixed size

layer_conv_3d_transpose

Transposed 3D convolution layer (sometimes called Deconvolution).

Flattens an input

layer_global_average_pooling_1d

Global average pooling operation for temporal data.

Update the value of x by adding increment.

k_spatial_2d_padding

Pads the 2nd and 3rd dimensions of a 4D tensor.

k_temporal_padding

Pads the middle dimension of a 3D tensor.

Element-wise sigmoid.

Element-wise tanh.

Returns the symbolic shape of a tensor or variable.

k_spatial_3d_padding

Pads 5D tensor with zeros along the depth, height, width dimensions.

Update the value of x by subtracting decrement.

layer_global_average_pooling_2d

Global average pooling operation for spatial data.

Reshapes an output to a certain shape.

Image resizing layer

Add a densely-connected NN layer to an output

layer_depthwise_conv_2d

Depthwise separable 2D convolution.

layer_discretization

A preprocessing layer which buckets continuous features by ranges.

layer_gaussian_noise

Apply additive zero-centered Gaussian noise.

Layer that adds a list of inputs.

layer_gaussian_dropout

Apply multiplicative 1-centered Gaussian noise.

Keras array object

layer_global_max_pooling_3d

Global Max pooling operation for 3D data.

layer_global_max_pooling_2d

Global max pooling operation for spatial data.

layer_activity_regularization

Layer that applies an update to the cost function based input activity.

layer_locally_connected_2d

Locally-connected layer for 2D inputs.

Base class for recurrent layers

layer_separable_conv_1d

Depthwise separable 1D convolution.

layer_max_pooling_1d

Max pooling operation for temporal data.

layer_random_width

Randomly vary the width of a batch of images during training

layer_random_zoom

A preprocessing layer which randomly zooms images during training.

Gated Recurrent Unit - Cho et al.

Cell class for the GRU layer

layer_spatial_dropout_1d

Spatial 1D version of Dropout.

layer_simple_rnn_cell

Cell class for SimpleRNN

layer_simple_rnn

Fully-connected RNN where the output is to be fed back to input.

layer_separable_conv_2d

Separable 2D convolution.

layer_random_translation

Randomly translate each image during training

layer_stacked_rnn_cells

Wrapper allowing a stack of RNN cells to behave as a single cell

layer_max_pooling_2d

Max pooling operation for spatial data.

Permute the dimensions of an input according to a given pattern

layer_rescaling

Multiply inputs by scale and adds offset

layer_random_rotation

Randomly rotate each image

Layer that computes the maximum (element-wise) a list of inputs.

layer_max_pooling_3d

Max pooling operation for 3D data (spatial or spatio-temporal).

layer_string_lookup

A preprocessing layer which maps string features to integer indices.

layer_repeat_vector

Repeats the input n times.

layer_random_brightness

A preprocessing layer which randomly adjusts brightness during training

Long Short-Term Memory unit - Hochreiter 1997.

layer_zero_padding_2d

Zero-padding layer for 2D input (e.g. picture).

layer_zero_padding_1d

Zero-padding layer for 1D input (e.g. temporal sequence).

layer_normalization

A preprocessing layer which normalizes continuous features.

Layer that multiplies (element-wise) a list of inputs.

layer_upsampling_1d

Upsampling layer for 1D inputs.

layer_unit_normalization

Unit normalization layer

layer_zero_padding_3d

Zero-padding layer for 3D data (spatial or spatio-temporal).

layer_random_flip

Randomly flip each image horizontally and vertically

layer_random_height

Randomly vary the height of a batch of images during training

learning_rate_schedule_cosine_decay

A LearningRateSchedule that uses a cosine decay schedule

loss_cosine_proximity

(Deprecated) loss_cosine_proximity

make_sampling_table

Generates a word rank-based probabilistic sampling table.

learning_rate_schedule_polynomial_decay

A LearningRateSchedule that uses a polynomial decay schedule

layer_upsampling_2d

Upsampling layer for 2D inputs.

learning_rate_schedule_cosine_decay_restarts

A LearningRateSchedule that uses a cosine decay schedule with restarts

layer_upsampling_3d

Upsampling layer for 3D inputs.

metric_false_negatives

Calculates the number of false negatives

metric_false_positives

Calculates the number of false positives

metric_categorical_accuracy

Calculates how often predictions match one-hot labels

metric_binary_crossentropy

Computes the crossentropy metric between the labels and predictions

metric_mean_squared_error

Computes the mean squared error between labels and predictions

metric_mean_squared_logarithmic_error

Computes the mean squared logarithmic error

layer_spatial_dropout_3d

Spatial 3D version of Dropout.

layer_spatial_dropout_2d

Spatial 2D version of Dropout.

metric_mean_iou

Computes the mean Intersection-Over-Union metric

layer_text_vectorization

A preprocessing layer which maps text features to integer sequences.

Layer that subtracts two inputs.

metric-or-Metric

metric-or-Metric

learning_rate_schedule_inverse_time_decay

A LearningRateSchedule that uses an inverse time decay schedule

learning_rate_schedule_piecewise_constant_decay

A LearningRateSchedule that uses a piecewise constant decay schedule

metric_cosine_proximity

(Deprecated) metric_cosine_proximity

metric_cosine_similarity

Computes the cosine similarity between the labels and predictions

learning_rate_schedule_exponential_decay

A LearningRateSchedule that uses an exponential decay schedule

metric_accuracy

Calculates how often predictions equal labels

metric_mean_relative_error

Computes the mean relative error by normalizing with the given values

metric_mean_wrapper

Wraps a stateless metric function with the Mean metric

metric_mean_tensor

Computes the element-wise (weighted) mean of the given tensors

Approximates the AUC (Area under the curve) of the ROC or PR curves

metric_logcosh_error

Computes the logarithm of the hyperbolic cosine of the prediction error

metric_binary_accuracy

Calculates how often predictions match binary labels

metric_true_negatives

Calculates the number of true negatives

metric_true_positives

Calculates the number of true positives

model_to_saved_model

(Deprecated) Export to Saved Model format

Computes the (weighted) mean of the given values

metric_recall_at_precision

Computes best recall where precision is >= specified value

Assign values to names

Model configuration as YAML

plot.keras_training_history

Plot training history

multi_gpu_model

(Deprecated) Replicates a model on different GPUs.

Reset the states for a layer

Remove the last layer in a model

metric_mean_absolute_error

Computes the mean absolute error between the labels and predictions

metric_mean_absolute_percentage_error

Computes the mean absolute percentage error between y_true and y_pred

regularizer_orthogonal

A regularizer that encourages input vectors to be orthogonal to each other

metric_root_mean_squared_error

Computes root mean squared error metric between y_true and y_pred

Gradient descent (with momentum) optimizer

Pads sequences to the same length

Model configuration as JSON

model_from_saved_model

Load a Keras model from the Saved Model format

metric_precision_at_recall

Computes best precision where recall is >= specified value

Computes the recall of the predictions with respect to the labels

metric_specificity_at_sensitivity

Computes best specificity where sensitivity is >= specified value

optimizer_adagrad

Optimizer that implements the Adagrad algorithm

metric_squared_hinge

Computes the squared hinge metric

Save/Load models using SavedModel format

metric_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions

metric_categorical_hinge

Computes the categorical hinge metric between y_true and y_pred

Normalize a matrix or nd-array

Text tokenization utility

Computes the Poisson metric between y_true and y_pred

Computes the hinge metric between y_true and y_pred

metric_kullback_leibler_divergence

Computes Kullback-Leibler divergence

Optimizer that implements the FTRL algorithm

metric_precision

Computes the precision of the predictions with respect to the labels

metric_sparse_top_k_categorical_accuracy

Computes how often integer targets are in the top K predictions

optimizer_adamax

Optimizer that implements the Adamax algorithm

metric_sparse_categorical_crossentropy

Computes the crossentropy metric between the labels and predictions

texts_to_matrix

Convert a list of texts to a matrix.

save_model_hdf5

Save/Load models using HDF5 files

Optimizer that implements the Adam algorithm

save_text_tokenizer

Save a text tokenizer to an external file

predict_on_batch

Returns predictions for a single batch of samples.

(Deprecated) Generates probability or class probability predictions for the input samples.

optimizer_adadelta

Optimizer that implements the Adadelta algorithm

sequential_model_input_layer

sequential_model_input_layer

metric_sparse_categorical_accuracy

Calculates how often predictions match integer labels

serialize_model

Serialize a model to an R object

Computes the (weighted) sum of the given values

metric_sensitivity_at_specificity

Computes best sensitivity where specificity is >= specified value

metric_top_k_categorical_accuracy

Computes how often targets are in the top K predictions

One-hot encode a text into a list of word indexes in a vocabulary of size n.

Generates skipgram word pairs.

Single gradient update or model evaluation over one batch of samples.

predict.keras.engine.training.Model

Generate predictions from a Keras model

new_learning_rate_schedule_class

Create a new learning rate schedule type

new_metric_class

Define new keras types

optimizer_nadam

Optimizer that implements the Nadam algorithm

text_to_word_sequence

Convert text to a sequence of words (or tokens).

use_implementation

Select a Keras implementation and backend

predict_generator

(Deprecated) Generates predictions for the input samples from a data generator.

optimizer_rmsprop

Optimizer that implements the RMSprop algorithm

sequences_to_matrix

Convert a list of sequences into a matrix.

text_dataset_from_directory

Generate a tf.data.Dataset from text files in a directory

plot.keras.engine.training.Model

Plot a Keras model

save_model_weights_tf

Save model weights in the SavedModel format

L1 and L2 regularization

save_model_weights_hdf5

Save/Load model weights using HDF5 files

Objects exported from other packages

texts_to_sequences_generator

Transforms each text in texts in a sequence of integers.

texts_to_sequences

Transform each text in texts in a sequence of integers.

with_custom_object_scope

Provide a scope with mappings of names to custom objects

summary.keras.engine.training.Model

Print a summary of a Keras model

time_distributed

This layer wrapper allows to apply a layer to every temporal slice of an input

timeseries_dataset_from_array

Creates a dataset of sliding windows over a timeseries provided as array

text_hashing_trick

Converts a text to a sequence of indexes in a fixed-size hashing space.

Converts a class vector (integers) to binary class matrix.

timeseries_generator

Utility function for generating batches of temporal data.